Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add asherzj/ashers-agent-skills --skill install-skillsgit clone --depth 1 https://github.com/asherzj/ashers-agent-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/asherzj/ashers-agent-skills/install-skills)<a href="https://agentmods.dev/skills/asherzj/ashers-agent-skills/install-skills"><img src="https://agentmods.dev/badge/skills/asherzj/ashers-agent-skills/install-skills/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/asherzj/ashers-agent-skills/install-skills"><img src="https://agentmods.dev/badge/skills/asherzj/ashers-agent-skills/install-skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00049 | $0.01518 |
| Opus 5 | $0.00024 | $0.00759 |
| Sonnet 5 | $0.00010 | $0.00304 |
| Haiku 4.5 | $0.00005 | $0.00152 |
Grade A, and why
install-skills scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- 如果克隆因网络问题失败，改用：`curl -sL --retry 3 -o /tmp/ashers-agent-skills.tar.gz https://codeload.github.com/asherzj/ashers-agent-skills/tar.gz/refs/heads/main` How it starts
The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
选择并安装 Skill
把 https://github.com/asherzj/ashers-agent-skills 中用户选择的分类安装到当前 Coding Agent 的用户级 Skill 目录。重复选择同一分类即为升级。
根目录下的 install-skills 是仓库唯一的安装入口，不属于任何内容分类。每次运行都同步安装或升级它自身，方便用户以后再次选择分类；分类内容只按用户本次选择处理。
1. 让用户选择分类
可选分类：
coding：27 个编码与软件研发 Skill；career：1 个求职准备 Skill：write-resume；writing：当前 0 个 Skill，选择后只报告暂无可安装内容；all：选择全部三个分类。
支持多选，例如 coding + career。如果用户在调用时已经明确给出分类，直接采用该选择；否则先展示上述清单并询问：
请选择要安装或升级的分类：coding、career、writing，或 all。可以多选；安装器 install-skills 自身会一并更新。
这是安装范围的 human-in-the-loop 门禁。在用户明确选择前可以做只读检查，但不得向用户级 Skill 目录写入内容。用户选择后，Agent 全权完成源码获取、扫描、冲突检查、复制、验证、清理和汇报，不再要求用户逐个确认 Skill。
本次未选择的分类不得安装、升级或删除；目标目录中原有的其他 Skill 也必须保留。
2. 定位用户级 Skill 目录
安装目录因 Agent 而异，例如 Claude Code 使用 ~/.claude/skills，Codex 通常使用 ~/.codex/skills。优先读取当前 Agent 的配置约定；仍无法确定时询问用户，不能猜测路径后直接写入。
如果必须询问安装目录，可以和分类选择合并为一次提问。写入前向用户明确展示解析后的目标目录和所选分类；用户先前已经明确指定二者时不重复确认。
3. 获取仓库源码
- 优先使用：
git clone --depth 1 https://github.com/asherzj/ashers-agent-skills.git /tmp/ashers-agent-skills - 如果克隆因网络问题失败，改用：
curl -sL --retry 3 -o /tmp/ashers-agent-skills.tar.gz https://codeload.github.com/asherzj/ashers-agent-skills/tar.gz/refs/heads/main
如果当前工作目录已经是该仓库的有效检出，可以直接使用；否则只在明确、独立的临时目录中获取源码，不能把用户的工作目录当作安装暂存区。
4. 解析安装范围
始终把根目录下直接包含 SKILL.md 的 install-skills/ 加入安装清单。然后只扫描用户选择的分类目录，并只安装其中直接包含 SKILL.md 的一级子目录。
当前预期数量为：根级 install-skills 1 个；coding 27 个，包括 6 个封装流程、20 个工程模块和 grilling 访谈原语；career 1 个；writing 0 个。选择 all 时合计安装 29 个 Skill。分类目录和说明性 README.md 不作为 Skill 安装，也不要递归猜测更深层级。
安装前检查所选分类之间以及与根级安装器之间是否存在重复 Skill 名称。发现重名时停止写入并报告冲突，不能按扫描顺序静默覆盖。
关键依赖关系：
flow-feature→from-transcript（按需）、grill-with-docs、prototype、to-spec、to-tickets、implementflow-small-change→from-transcript（按需）、grill-with-docs、implementflow-incoming-issue→triage、implementflow-hard-bug→diagnosing-bugs、implement、code-reviewflow-large-effort→from-transcript（按需）、wayfinder、to-spec、to-tickets、implementflow-architecture-maintenance→improve-codebase-architecture、to-spec、to-tickets、implement、context-gcfrom-transcript→grilling、domain-modelingcontext-gc→grilling、domain-modelinggrill-with-docs→grilling、domain-modelingimprove-codebase-architecture→codebase-design、domain-modeling、grillingwayfinder→domain-modeling、grilling、prototype、researchsetup-engineering-skills提供triage、wayfinder、to-spec、to-tickets使用的仓库级配置
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 86 lines · 49 tokens per session scan A ce8597c16f08
install-skills is a skill published in the GitHub repository asherzj/ashers-agent-skills (2 stars, last pushed 13d ago), licensed MIT. It adds 49 tokens to every session and 1,518 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…